Apex system helps build flexible production schedules with agent support
APEX: An Extensible Model for Agent-Assisted Production Scheduling
Artificial IntelligenceNeural and Evolutionary Computing
Summary
Scheduling jobs in factories is tricky because many rules and goals must be balanced. The authors present APEX, a flexible system that uses smart helpers called agents to handle data, test changes, and create schedules. These agents can communicate in everyday language to explore what-if scenarios and update plans easily. The system was tested on many scheduling problems and compared with other methods, often performing best overall. It also proved capable of safely adding new rules without changing the system’s core.
What this means in practice
- •For manufacturing planners: Create flexible production schedules that integrate realistic rules and adapt through natural language interaction without rewriting core code.
- •For industrial software developers: Implement and test new scheduling objectives or constraints in production planning systems through predefined extension points safely.
Authors
Felix J. Grumbach, Stefan Görlitz
Abstract
Production scheduling requires realistic models that reflect operational constraints and efficient methods that balance competing goals. Putting these methods into use also requires data integration, model adaptation and specialist expertise. We present APEX, an extensible production scheduling framework built around a general model and hybrid multiobjective search. Agent assistance supports both scheduling and model refinement: agents prepare data and explore scenarios in natural language, while coding agents help implement and test new constraints and objectives. Shared construction and checking procedures connect these adaptations to the scheduling core. We benchmark eight APEX configurations against NSGA-II, SPEA2, MOEA/D and SMS-EMOA on 69 public job-shop, flexible job-shop and permutation flow-shop instances, assessing workload completion time (makespan), total job flowtime and computation time. Hybrid configurations achieve the best aggregate solution quality, although the leading method depends on the problem class and objective. A separate synthetic workflow study uses OpenAI's GPT-6-astra as an interaction layer between the human planner and the algorithmic core, testing rule additions, plan and objective changes, and what-if comparisons. All 24 sessions completed the requested changes and passed independent checks of saved models and schedules. A separate coding evaluation produced six native implementations of an additional objective or hard constraint through predefined extension hooks. All passed independent checks without modifying the core.